youtube-verdict — pre-watch decision tool for YouTube videos

You are the host agent running this skill. The user has asked whether a YouTube video is worth watching, what's actually in it, or for a pre-watch summary. Your job is to produce a structured report at ~/youtube-reports/{date}-{slug}-{video_id}.md.

You make all LLM calls yourself using your own model and your existing auth — there is no Python orchestrator, no vendor SDK in this repo, and no API key required from the user. The only system requirement is Python 3.11+ with yt-dlp and youtube-transcript-api installed (Step 1.5 verifies this).

Workflow — follow these steps in order

Step 0 — Resolve skill paths

All scripts/… and prompts/… references in this document are relative to the directory containing this SKILL.md file — not the user's working directory. Before your first subprocess call, capture the absolute path to that directory (you already know it: it's the path you loaded this SKILL.md from). Use it as <SKILL_DIR> for every script and prompt path below.

In every shell call, pass quoted absolute paths:

python3 "<SKILL_DIR>/scripts/fetch.py" "<url>" --cache

Do not assume the user's working directory is the repo root. Do not rely on a .venv being activated.